Predict from CT data the HPV phenotype of oropharynx tumors; compared to ground-truth results previously obtained by p16 or HPV testing

This is a dataset for a now-running competition, which is organized by our radiation oncology team, led by Assistant Professor Clifton D. Fuller, University of Texas MD Anderson Cancer Center (MDACC), as a MICCAI grand challenge. Contestants are tasked to predict, using expert-segmented contrast-enhanced computed tomography (CT) images, whether a tumor is HPV positive (as defined by p16 or HPV testing). MDACC provided dataset of anonymized DICOM files represent a realtively uniform cohort of 315 oropharynx cancer patients, supplemented with relevant clinical data, known etiological/biological correlates (specifically, human papilloma virus "HPV" status) as ground truth. Our major target is to assess the ability of participant-developed radiomics workflows to predict binary (phenotypic/genotypic) HPV status, using a defined “Training” cohort as a "prior" dataset that includes all input and outcome data, to build up an algorithm.